© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14419
    Prev
    Next
    INDEX
    Explanations

    numbers in the format of a colon followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bered
    -0.84
     tremend
    -0.74
    rave
    -0.73
    omething
    -0.70
    uve
    -0.69
     inward
    -0.67
     eaves
    -0.67
    inement
    -0.66
    bus
    -0.66
     behav
    -0.65
    POSITIVE LOGITS
     Unknown
    1.04
     TBA
    1.02
     None
    1.02
     TBD
    0.98
     ???
    0.96
     Provided
    0.95
     Ibid
    0.87
     Nope
    0.85
     Yes
    0.82
     Various
    0.82
    Activations Density 0.089%

    No Known Activations